autonomy for general assembly reid simmons research professor robotics institute carnegie mellon...

17
Autonomy for General Assembly Autonomy for General Assembly Reid Simmons Research Professor Robotics Institute Carnegie Mellon University

Upload: arline-armstrong

Post on 18-Jan-2016

212 views

Category:

Documents


0 download

TRANSCRIPT

Page 1: Autonomy for General Assembly Reid Simmons Research Professor Robotics Institute Carnegie Mellon University

Autonomy for General AssemblyAutonomy for General Assembly

Reid SimmonsResearch ProfessorRobotics Institute

Carnegie Mellon University

Page 2: Autonomy for General Assembly Reid Simmons Research Professor Robotics Institute Carnegie Mellon University

Autonomy for General Assembly Carnegie Mellon2

The ChallengeThe Challenge

• Autonomous manipulation of flexible objects for general assembly of vehicles– Dexterity

– Precise perception

– Speed

– Reliability

• The Specific Task– Insert clip attached to cable into

hole with millimeter tolerance

– Year 2: Moving taskboard

Page 3: Autonomy for General Assembly Reid Simmons Research Professor Robotics Institute Carnegie Mellon University

Autonomy for General Assembly Carnegie Mellon3

Overall ApproachOverall Approach

• Utilize our previous work in robot autonomy– Multi-layered software architecture

– Hierarchical, task-level description of assembly

– Robust, low-level behaviors

– Distributed visual servoing

– Force sensing

– Exception detection and recovery

Page 4: Autonomy for General Assembly Reid Simmons Research Professor Robotics Institute Carnegie Mellon University

Autonomy for General Assembly Carnegie Mellon4

Architectural FrameworkArchitectural Framework

Deals with goals and resource interactionsTask decomposition; Task synchronization; Monitoring; Exception handlingDeals with sensors and actuators

• Three-Tiered Architecture

• Reactive & Deliberative• Modular• Control loops at multiplelevels of abstraction

Executive

BehavioralControl

Planning

Page 5: Autonomy for General Assembly Reid Simmons Research Professor Robotics Institute Carnegie Mellon University

Autonomy for General Assembly Carnegie Mellon5

Syndicate: Multi-Robot ArchitectureSyndicate: Multi-Robot ArchitectureSynchronization / Coordination

Gra

nula

tity

Executive

BehavioralControl

Planning

Executive

BehavioralControl

Executive

BehavioralControl

Planning Planning

Page 6: Autonomy for General Assembly Reid Simmons Research Professor Robotics Institute Carnegie Mellon University

Autonomy for General Assembly Carnegie Mellon6

Syndicate Layers: BehavioralSyndicate Layers: Behavioral

• Made up of “blocks”– Each block is a small thread/function/process

– Represent hardware capabilities or repeatable behaviors

– “Stateless”: relies on current data; no knowledge of past or future

• Communicate with sensors

• Send commands to robots and get feedback

• Communicate data to other blocks

Page 7: Autonomy for General Assembly Reid Simmons Research Professor Robotics Institute Carnegie Mellon University

Autonomy for General Assembly Carnegie Mellon7

Ace Control BehaviorsAce Control Behaviors

Page 8: Autonomy for General Assembly Reid Simmons Research Professor Robotics Institute Carnegie Mellon University

Autonomy for General Assembly Carnegie Mellon8

Distributed Visual ServoingDistributed Visual Servoing• Mast Eye tracks fiducials

– Uses ARTag software package to detect fiducials– Provides 6-DOF transform between fiducials

• Mobile Manipulator uses information to plan how to achieve goal– Use data base describing positions of fiducials on objects

• Behavioral layer enables dynamic, transparent inter-agent connections

Mobile Manipulator

VisualServoRelativepositions

ArmControl

End effector delta

Mast Eye

Tracking

Images (via cameras)

The World

Manipulate environment (via arm)

Page 9: Autonomy for General Assembly Reid Simmons Research Professor Robotics Institute Carnegie Mellon University

Autonomy for General Assembly Carnegie Mellon9

Distributed Visual ServoingDistributed Visual Servoing

• Fairly precise– millimeter resolution at one meter

• Relatively fast– 3-4 Hz

• Basically unchanged from Trestle code

• Operates in relative frame– Poses of one object relative to another

– Controller continually tries to reduce pose difference

– Cameras do not need to be precisely calibrated with respect to base or arm

Page 10: Autonomy for General Assembly Reid Simmons Research Professor Robotics Institute Carnegie Mellon University

Autonomy for General Assembly Carnegie Mellon10

Distributed Visual ServoingDistributed Visual Servoing

• Associating Fiducials with Objects– Programmer provides file listing the pose of each fiducial

with respect to an object

– Multiple fiducials can be associated with each object

– Can measure directly, or use system to give us the poses

• Reducing Pose Differences– “Waypoint” is the pose of one object with respect to another

• Everything is relative!

– Visual servo block multiplies pose difference by gain

– Update moves when new information arrives

Page 11: Autonomy for General Assembly Reid Simmons Research Professor Robotics Institute Carnegie Mellon University

Autonomy for General Assembly Carnegie Mellon11

Syndicate Layers: ExecutiveSyndicate Layers: Executive

• Made up of “tasks”– Each task is concerned with achieving a single goal

– Tasks can be arranged temporally

• Tasks can:– Spawn subtasks

– Enable and connect blocks in the behavioral layer to achieve the task

• Enable tell a block to start running

• Connect tell blocks to send data to other blocks

– Monitor blocks for failure

– Provide failure recovery

Page 12: Autonomy for General Assembly Reid Simmons Research Professor Robotics Institute Carnegie Mellon University

Autonomy for General Assembly Carnegie Mellon12

Ace Task DecompositionAce Task Decomposition

Child link

Serial Constraint

Page 13: Autonomy for General Assembly Reid Simmons Research Professor Robotics Institute Carnegie Mellon University

Autonomy for General Assembly Carnegie Mellon13

Example TDL Code (somewhat simplified)Example TDL Code (somewhat simplified)

Goal ClipInsertion ( ) {

loadPlugArmPose : spawn ArmMove (loadPose);

stowArmPose: spawn ArmMove (stowPose) WITHSERIAL loadPlugArmPose;

roughBaseMove: spawn RoughBaseMove (roughBaseWaypoint)

WITH SERIAL loadPlugArmPose;

spawn RoughArmMove (roughArmWaypoint)WITH SERIAL roughBaseMove, SERIAL stowArmPose;

…}

A keyword that says this is not supposed to be a “leaf” in the task tree

Reusing task with different parameters

In the tree, this is the task name, but this is the actual function being executed

Tells the system to execute this task

after LoadPlugArmPose completes

Wait until both tasks have completed before starting RoughArmMove

Page 14: Autonomy for General Assembly Reid Simmons Research Professor Robotics Institute Carnegie Mellon University

Autonomy for General Assembly Carnegie Mellon14

Initial Results (December 2007)Initial Results (December 2007)

• Used Previous Hardware– RWI base

– Metrica 5 DOF arm

– Metal & plastic gripper

• Successfully Inserted Clip– 60% success rate (15 trials)

• Mainly attributable to hardware problems

– Fairly slow (~1 minute)

– Scripted base move

Page 15: Autonomy for General Assembly Reid Simmons Research Professor Robotics Institute Carnegie Mellon University

Autonomy for General Assembly Carnegie Mellon15

Insertion VideoInsertion Video

Page 16: Autonomy for General Assembly Reid Simmons Research Professor Robotics Institute Carnegie Mellon University

Autonomy for General Assembly Carnegie Mellon16

Current StatusCurrent Status• Moved to New Hardware

– Powerbot base– WAM arm (Barrett)– All-metal gripper

• Still Successfully Inserting Clip– Much faster

• Better hardware• “Rough” moves

– Base motion is planned, not scripted– Uses force sensing to detect completion / problem– Have not yet characterized success rate

Page 17: Autonomy for General Assembly Reid Simmons Research Professor Robotics Institute Carnegie Mellon University

Autonomy for General Assembly Carnegie Mellon17

Upcoming WorkUpcoming Work• Near Term (1 month)

– Complete hardware integration• Laser, PTU, VizTracker

– Characterize success rate of system

• Mid Term (2-6 months)– Convert to velocity control of WAM– Use force control for actual insertion– Increase reliability through execution monitoring and

exception handling

• Farther Term (2nd year of contract)– Insert clip into moving taskboard